544 tokens per sec - the new SPEED RECORD on GPUs with Clarifai Reasoning Engine! #gptoss #ai
We just launched our new Reasoning Engine cranking gpt-oss 120b to 544 tokens per second, a new throughput record for model performance on GPUs. World class speed at only $0.16 per 1M tokens - learn more here: https://www.clarifai.com/products/model-inference